detect_density.py

import argparse
import time
from pathlib import Path

import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random

from models.experimental import attempt_load
from utils.datasets import LoadStreams, LoadImages
from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
    scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
from utils.plots import plot_one_box
from utils.torch_utils import select_device, load_classifier, time_synchronized
import json
import numpy as np
import matplotlib.pyplot as plt

def detect(save_img=False):
    source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
    # Directories
    save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run
    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
    # Initialize
    set_logging()
    device = select_device(opt.device)
    half = device.type != 'cpu'  # half precision only supported on CUDA
    # Load model
    model = attempt_load(weights, map_location=device)  # load FP32 model
    stride = int(model.stride.max())  # model stride
    imgsz = check_img_size(imgsz, s=stride)  # check img_size
    print("detect image size == >",imgsz)
    if half:
        model.half()  # to FP16
    # Set Dataloader
    vid_path, vid_writer = None, None
    save_img = True
    dataset = LoadImages(source, img_size=imgsz, stride=stride)
    # Get names and colors
    names = model.module.names if hasattr(model, 'module') else model.names
    # colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
    # 'fake','negative','others','positive'
    colors = [[200,0,0],[0,200,200],[0,200,0],[0,0,200]]
    # Run inference
    if device.type != 'cpu':
        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
    t0 = time.time()
    for path, img, im0s, vid_cap in dataset:
        imagePath = path.split('/')[-1]
        print('image path=>',imagePath)
        img = torch.from_numpy(img).to(device)
        img = img.half() if half else img.float()  # uint8 to fp16/32
        img /= 255.0  # 0 - 255 to 0.0 - 1.0
        if img.ndimension() == 3:
            img = img.unsqueeze(0)
        # Inference
        t1 = time_synchronized()
        (pred,_), density_map_out = model(img, augment=opt.augment)
        print('density_map_out => ', density_map_out.shape)
        ################看数据的大小#################################################
        if density_map_out.shape[1] > 1: # 多类别
            fileName = imagePath.replace('.png', '')
            source_img = np.copy(img.cpu())
            density_img0 = np.copy(density_map_out[0][0].cpu())
            density_img1 = np.copy(density_map_out[0][1].cpu())
            density_img2 = np.copy(density_map_out[0][2].cpu())
            density_img3 = np.copy(density_map_out[0][3].cpu())
            # 密度图叠加到一起
            density_overlap = np.ones([160,160])
            density_overlap[0:80,0:80] = density_img0
            density_overlap[0:80,80:160] = density_img1
            density_overlap[80:160,0:80] = density_img2
            density_overlap[80:160,80:160] = density_img3

            plt.imsave(f'all_{fileName}.png', density_overlap)

            print(source_img.shape, density_img0.shape, density_img1.shape, density_img2.shape, density_img3.shape)
            print('----> ', f'./detect_density_out/{fileName}_source_img.png')
            plt.imsave(f'./detect_density_out/{fileName}_source_img.png', source_img[0].transpose(1,2,0))
            plt.imsave(f'./detect_density_out/{fileName}_density_map_out0.png', density_img0)
            plt.imsave(f'./detect_density_out/{fileName}_density_map_out1.png', density_img1)
            plt.imsave(f'./detect_density_out/{fileName}_density_map_out2.png', density_img2)
            plt.imsave(f'./detect_density_out/{fileName}_density_map_out3.png', density_img3)
        else:  # 单类别
            fileName = imagePath.replace('.png', '')
            source_img = np.copy(img.cpu())
            density_img0 = np.copy(density_map_out[0][0].cpu())
            plt.imsave(f'./detect_density_out/{fileName}_source_img.png', source_img[0])
            plt.imsave(f'./detect_density_out/{fileName}_density_map_out0.png', density_img0)
        #############################################################################
        # Apply NMS
        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
        t2 = time_synchronized()
        # Process detections
        for i, det in enumerate(pred):  # detections per image
            p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)

            p = Path(p)  # to Path
            save_path = str(save_dir / p.name)  # img.jpg
            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # img.txt
            s += '%gx%g ' % img.shape[2:]  # print string
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
            if len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
                # Print results
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  # detections per class
                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
                # Write results
                # 输出细胞检测的结果
                cellResult = {}
                cellResult['version'] = '4.5.7'
                cellResult['flags'] = {}
                cellResult['shapes'] = []
                #数据存储到本地
                cellResult['imagePath'] = imagePath
                cellResult['imageData'] = None
                cellResult['imageHeight'] = 512
                cellResult['imageWidth'] = 512
                for *xyxy, conf, cls in reversed(det):
                    cellShape = {}
                    if save_txt and False:  # Write to file
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                        line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh)  # label format
                        with open(txt_path + '.txt', 'a') as f:
                            f.write(('%g ' * len(line)).rstrip() % line + '\n')

                    if save_img or view_img:  # Add bbox to image
                        label = f'{names[int(cls)]} {conf:.2f}'
                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)
                    # 保存标签的json
                    if opt.save_label_json:
                        label = f'{names[int(cls)]}'
                        cellShape['label'] = label
                        cellShape['points'] = []
                        cellShape['points'].append([xyxy[0].data.cpu().numpy().tolist(),xyxy[1].data.cpu().numpy().tolist()])
                        cellShape['points'].append([xyxy[2].data.cpu().numpy().tolist(),xyxy[3].data.cpu().numpy().tolist()])
                        cellShape['group_id'] = None
                        cellShape['shape_type'] = 'rectangle'
                        cellShape['flags'] = {}
                        cellResult['shapes'].append(cellShape)

                with open(txt_path+'.json','w') as file:
                    print('保存的文件路径 ==> '+txt_path+'.json')
                    json.dump(cellResult,file)
            # Print time (inference + NMS)
            print(f'{s}Done. ({t2 - t1:.3f}s)')
            # Stream results
            if view_img:
                cv2.imshow(str(p), im0)
                cv2.waitKey(1)  # 1 millisecond

            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'image':
                    cv2.imwrite(save_path, im0)
                else:  # 'video'
                    if vid_path != save_path:  # new video
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.release()  # release previous video writer

                        fourcc = 'mp4v'  # output video codec
                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h))
                    vid_writer.write(im0)

    if save_txt or save_img:
        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
        print(f"Results saved to {save_dir}{s}")

    print(f'Done. ({time.time() - t0:.3f}s)')


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    # runs/train/a_0.25_b_1.5/weights/best.pt runs/train/yolo-baseline/weights/best.pt
    # runs/train/localunet_density_multi/weights/best.pt
    parser.add_argument('--weights', nargs='+', type=str, default='runs/train/localunet_density_multi/weights/best.pt', help='model.pt path(s)')
    # parser.add_argument('--source', type=str, default='../ki67Dataset/AllImage/val/images', help='source')
    parser.add_argument('--source', type=str, default='analysisData', help='source')
    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.4, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
    parser.add_argument('--device', default='0,1', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--view-img', action='store_true', help='display results')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--save-json', action='store_true', help='save results to *.json')
    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--update', action='store_true', help='update all models')
    parser.add_argument('--project', default='runs/detect', help='save results to project/name')
    parser.add_argument('--name', default='exp', help='save results to project/name')
    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--save-label-json', default=True, action='store_true', help='save label results to *.json')
    # save_label_json
    opt = parser.parse_args()
    print(opt)
    check_requirements()
    opt.save_txt = True
    with torch.no_grad():
        if opt.update:  # update all models (to fix SourceChangeWarning)
            for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
                detect()
                strip_optimizer(opt.weights)
        else:
            detect()